AiCostCompare

Compare models

Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.

Gemini 3.6 FlashGPT-4o-mini
Gemini 3.6 Flash

Google

GPT-4o-mini

OpenAI

Pricing
Input $/1M$1.50$0.15
Output $/1M$7.50$0.60
Blended $/1M (3:1)$3.00$0.262
Cache read $/1M$0.15$0.075
Cache write $/1M$0.083
Quality indices
Intelligence Index50.16.9
Coding Index69.211.4
Math Index14.7
Agentic Index38.71
Speed & latency
Output speed (tok/s)30188
Time to first token11.80s0.60s
Time to first answer token11.80s0.60s
Benchmarks (Artificial Analysis)
MMLU-Pro64.8%
GPQA Diamond92.8%42.6%
Humanity's Last Exam38.3%4.0%
LiveCodeBench23.4%
SciCode52.7%22.9%
MATH-50078.9%
AIME11.7%
AIME 202514.7%
IFBench31.0%
AA-LCR (Long Context Reasoning)69.7%
Terminal-Bench 2.177.5%5.6%
τ³-Bench Banking24.5%2.9%
Design Arena (Elo)
Website1,332
Specs
Context window1.05M128K
Max output tokens66K16K
Input modalitiestext, image, video, file, audiotext, image, file
TokenizerGeminiGPT